Number of rows and columns

# Load libraries
library(tidyverse)
library(palmerpenguins)
library(GGally)
library(plotly)
library(caret)

# Dataset overview
data <- penguins
cat("Number of penguins: ", nrow(penguins), "\n")

## Number of penguins:  344

cat("Variables: ", names(penguins), "\n\n")

## Variables:  species island bill_length_mm bill_depth_mm flipper_length_mm body_mass_g sex year

cat("Missing values per variable:\n")

## Missing values per variable:

print(colSums(is.na(penguins)))

##           species            island    bill_length_mm     bill_depth_mm 
##                 0                 0                 2                 2 
## flipper_length_mm       body_mass_g               sex              year 
##                 2                 2                11                 0

# Species distribution
penguins %>% count(species)

## # A tibble: 3 × 2
##   species       n
##   <fct>     <int>
## 1 Adelie      152
## 2 Chinstrap    68
## 3 Gentoo      124

histo_species <- ggplot(penguins) +
  geom_bar(aes(x = species), fill = "darkorchid4", color = "darkgray") +
  labs(title = "Penguin Species", subtitle = "Bar chart", y = "Count") +
  theme_light()
histo_species

# Island distribution
penguins %>% count(island)

## # A tibble: 3 × 2
##   island        n
##   <fct>     <int>
## 1 Biscoe      168
## 2 Dream       124
## 3 Torgersen    52

histo_isl <- ggplot(penguins) +
  geom_bar(aes(x = island), fill = "darkorchid4", color = "darkgray") +
  labs(title = "Number of Penguins per Island", subtitle = "Bar chart", y = "Count") +
  theme_light()
histo_isl

# Univariate analysis
body_mass_plot <- ggplot(penguins, aes(x = species, y = body_mass_g, fill = species)) +
  geom_boxplot() +
  labs(title = "Body Mass by Species") +
  theme_light()
 
body_mass_plot

bill_len_plot <- ggplot(penguins, aes(x = species, y = bill_length_mm, fill = species)) +
  geom_boxplot() +
  labs(title = "Bill Length by Species") +
  theme_light()
bill_len_plot

flipper_len_plot <- ggplot(penguins, aes(x = species, y = flipper_length_mm, fill = species)) +
  geom_boxplot() +
  labs(title = "Flipper Length by Species") +
  theme_light()
flipper_len_plot

# These histogram are showing features differences between species. With the first histogram, Gentoos are nearly 1kg heavier than others, Adelie's bills are smaller and Gentoos have a bigger flipper. 
# Bivariate analysis
body_mass_and_flipper_length <- ggplot(penguins, aes(x = body_mass_g, y = flipper_length_mm, color = species)) +
  geom_point() +
  geom_smooth(method = "lm", se = FALSE) +
  labs(title = "Body Mass vs Flipper Length") +
  theme_light()
#We search a potential correlation between body mass and flipper length. That plot shows us a positive correlation, the heavier entities are the bigger their flipper is. 
body_mass_and_flipper_length

bill_len_and_sex_plot <- ggplot(penguins, aes(x = species, y = bill_length_mm, fill = sex)) +
  geom_boxplot(position = position_dodge()) +
  labs(title = "Bill Length by Sex and Species") +
  theme_light()
bill_len_and_sex_plot

isl_and_species_plot <- ggplot(penguins, aes(x = island, fill = species)) +
  geom_bar(position = "dodge") +
  labs(title = "Penguin Species Distribution Across Islands") +
  theme_light()
isl_and_species_plot

# Multivariate analysis
features_by_species_plot <- penguins %>%
  select(species, bill_length_mm, bill_depth_mm, flipper_length_mm, body_mass_g)
ggpairs(features_by_species_plot, aes(color = species, alpha = 0.6))

# From this plot, we observe 3 clear cluster of species and features. 
plot_ly(
  data = penguins,
  x = ~bill_length_mm,
  y = ~flipper_length_mm,
  z = ~body_mass_g,
  color = ~species,
  colors = c("Adelie" = "blue", "Gentoo" = "green", "Chinstrap" = "red"),
  type = "scatter3d",
  mode = "markers"
)

mass_sex_species <- ggplot(penguins, aes(x = species, y = body_mass_g, fill = sex)) +
  geom_boxplot(position = position_dodge()) +
  labs(title = "Body Mass by Sex and Species") +
  theme_light()
mass_sex_species

#As we saw 3 clusters on the 3d plot, we train a knn to predict species. We already know the parameter (3). 
# K-means clustering
penguins_num <- penguins %>%
  select(bill_length_mm, bill_depth_mm, flipper_length_mm, body_mass_g) %>%
  drop_na()

set.seed(123)
km <- kmeans(scale(penguins_num), centers = 3)

penguins_clustered <- penguins %>%
  drop_na(bill_length_mm, bill_depth_mm, flipper_length_mm, body_mass_g) %>%
  mutate(cluster = factor(km$cluster))

plot_ly(
  data = penguins_clustered,
  x = ~bill_length_mm,
  y = ~flipper_length_mm,
  z = ~body_mass_g,
  color = ~cluster,
  type = "scatter3d",
  mode = "markers"
)

# Confusion matrix
conf_matrix <- table(Cluster = penguins_clustered$cluster, Species = penguins_clustered$species)
conf_matrix

##        Species
## Cluster Adelie Chinstrap Gentoo
##       1      0         0    123
##       2    143         5      0
##       3      8        63      0

#That confusion matrix confirm our model, we achieve a good accuracy with low false positive especially for Gentoos. Our model is validated.

Report

2025-09-12

Analysis on penguins dataset

Number of rows and columns